DataFrame.groupby
Group DataFrame using a mapper or by a Series of columns.
danfo.DataFrame.groupby(columns)
Parameters
Type
Description
Default
columns
Array
The names of a column(s) in the DataFrame to group by
Examples
Groupby a single column from a DataFrame
Node
Browser
1
const dfd = require("danfojs-node")
2
3
let data = [["Pear", 2, 3], ["Pear", 5, 6], ["Apple", 30, 40], ["Apple", 89, 78]]
4
let cols = ["A", "B", "C"]
5
6
let df = new dfd.DataFrame(data, { columns: cols })
7
let group_df = df.groupby(["A"])
8
console.log(group_df)
Copied!
1
// ouput
2
Groupby {
3
colDict: {
4
Pear: { A: [Array], B: [Array], C: [Array] },
5
Apple: { A: [Array], B: [Array], C: [Array] }
6
},
7
keyToValue: { Pear: [ 'Pear' ], Apple: [ 'Apple' ] },
8
keyCol: [ 'A' ],
9
data: [
10
[ 'Pear', 2, 3 ],
11
[ 'Pear', 5, 6 ],
12
[ 'Apple', 30, 40 ],
13
[ 'Apple', 89, 78 ]
14
],
15
columnName: [ 'A', 'B', 'C' ],
16
colDtype: [ 'string' ],
17
colIndex: [ 0 ]
18
}
Copied!
1
Copied!
A groupby operation will return a GroupBy class object. You can apply any of the following operation on the groupby result:
Example of Groupby and apply a sum function
Node
1
const dfd = require("danfojs-node")
2
3
let data = [["Pear", 2, 3], ["Pear", 5, 6], ["Apple", 30, 40], ["Apple", 89, 78]]
4
let cols = ["A", "B", "C"]
5
let df = new dfd.DataFrame(data, { columns: cols })
6
let group_df = df.groupby(["A"]).sum()
7
8
group_df.print()
Copied!
1
╔════════════╤═══════════════════╤═══════════════════╤═══════════════════╗
2
║ │ A │ B_sum │ C_sum ║
3
╟────────────┼───────────────────┼───────────────────┼───────────────────╢
4
║ 0 │ Pear │ 7 │ 9 ║
5
╟────────────┼───────────────────┼───────────────────┼───────────────────╢
6
║ 1 │ Apple │ 119 │ 118 ║
7
╚════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
Copied!
Groupby a two columns from a DataFrame
Node
Browser
1
const dfd = require("danfojs-node")
2
3
let data = [["Pear", 2, 3], ["Pear", 2, 6], ["Apple", 30, 40], ["Apple", 89, 78]]
4
let cols = ["A", "B", "C"]
5
let df = new dfd.DataFrame(data, { columns: cols })
6
let group_df = df.groupby(["A", "B"]).sum()
7
8
group_df.print()
Copied!
1
Copied!
1
╔════════════╤═══════════════════╤═══════════════════╤═══════════════════╗
2
║ │ A │ B │ C_sum ║
3
╟────────────┼───────────────────┼───────────────────┼───────────────────╢
4
║ 0 │ Pear │ 2 │ 9 ║
5
╟────────────┼───────────────────┼───────────────────┼───────────────────╢
6
║ 1 │ Apple │ 30 │ 40 ║
7
╟────────────┼───────────────────┼───────────────────┼───────────────────╢
8
║ 2 │ Apple │ 89 │ 78 ║
9
╚════════════╧═══════════════════╧═══════════════════╧═══════════════════╝
Copied!
Last modified 13d ago